Hugging Face's logo

Niharika1603
/
git-base-instagram-captions

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Niharika1603 commited on
Commit
1738535
·
verified ·
1 Parent(s): 30f0d72

Model save

Browse files
Files changed (6) hide show
  1. README.md +116 -0
  2. config.json +1 -1
  3. generation_config.json +7 -0
  4. model.safetensors +1 -1
  5. runs/Jul14_03-54-49_d666e0c03635/events.out.tfevents.1720929290.d666e0c03635.919.0 +2 -2
  6. training_args.bin +2 -2
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/git-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: git-base-instagram-captions
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # git-base-instagram-captions
15
+
16
+ This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.8334
19
+ - Wer Score: 13.4415
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 20
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
+ |:-------------:|:-------:|:----:|:---------------:|:---------:|
53
+ | 4.3503 | 0.3556 | 20 | 4.0231 | 13.3087 |
54
+ | 3.2554 | 0.7111 | 40 | 3.0955 | 14.7696 |
55
+ | 2.7452 | 1.0667 | 60 | 2.5707 | 11.9736 |
56
+ | 1.916 | 1.4222 | 80 | 2.4606 | 14.1495 |
57
+ | 2.0349 | 1.7778 | 100 | 2.4337 | 15.4433 |
58
+ | 1.7522 | 2.1333 | 120 | 2.4274 | 13.5215 |
59
+ | 1.5496 | 2.4889 | 140 | 2.4298 | 13.0932 |
60
+ | 1.554 | 2.8444 | 160 | 2.4232 | 14.4336 |
61
+ | 1.3561 | 3.2 | 180 | 2.4537 | 13.2498 |
62
+ | 1.2081 | 3.5556 | 200 | 2.4563 | 14.3843 |
63
+ | 1.1593 | 3.9111 | 220 | 2.4378 | 14.3703 |
64
+ | 1.0503 | 4.2667 | 240 | 2.4849 | 14.6614 |
65
+ | 1.0292 | 4.6222 | 260 | 2.4937 | 14.5066 |
66
+ | 1.092 | 4.9778 | 280 | 2.4853 | 14.2252 |
67
+ | 0.8704 | 5.3333 | 300 | 2.5228 | 13.2709 |
68
+ | 0.8933 | 5.6889 | 320 | 2.5363 | 14.3369 |
69
+ | 0.8494 | 6.0444 | 340 | 2.5329 | 16.8566 |
70
+ | 0.7886 | 6.4 | 360 | 2.5424 | 13.8083 |
71
+ | 0.8338 | 6.7556 | 380 | 2.5585 | 13.6931 |
72
+ | 0.7756 | 7.1111 | 400 | 2.5856 | 14.4222 |
73
+ | 0.6575 | 7.4667 | 420 | 2.5890 | 13.6350 |
74
+ | 0.6793 | 7.8222 | 440 | 2.5833 | 14.1258 |
75
+ | 0.6439 | 8.1778 | 460 | 2.6046 | 15.0616 |
76
+ | 0.597 | 8.5333 | 480 | 2.6183 | 13.7511 |
77
+ | 0.6157 | 8.8889 | 500 | 2.6166 | 15.7696 |
78
+ | 0.6132 | 9.2444 | 520 | 2.6466 | 17.8857 |
79
+ | 0.5666 | 9.6 | 540 | 2.6472 | 16.8452 |
80
+ | 0.5691 | 9.9556 | 560 | 2.6456 | 13.7449 |
81
+ | 0.529 | 10.3111 | 580 | 2.6676 | 14.5945 |
82
+ | 0.5286 | 10.6667 | 600 | 2.6727 | 13.7344 |
83
+ | 0.5339 | 11.0222 | 620 | 2.6706 | 14.9833 |
84
+ | 0.4967 | 11.3778 | 640 | 2.6928 | 13.9587 |
85
+ | 0.459 | 11.7333 | 660 | 2.7035 | 14.5708 |
86
+ | 0.5117 | 12.0889 | 680 | 2.7064 | 14.3026 |
87
+ | 0.4424 | 12.4444 | 700 | 2.7304 | 14.0836 |
88
+ | 0.4829 | 12.8 | 720 | 2.7175 | 14.7573 |
89
+ | 0.4308 | 13.1556 | 740 | 2.7129 | 14.5928 |
90
+ | 0.3871 | 13.5111 | 760 | 2.7333 | 14.1328 |
91
+ | 0.4238 | 13.8667 | 780 | 2.7319 | 14.1759 |
92
+ | 0.4141 | 14.2222 | 800 | 2.7605 | 14.0580 |
93
+ | 0.3435 | 14.5778 | 820 | 2.7604 | 13.6966 |
94
+ | 0.3807 | 14.9333 | 840 | 2.7634 | 13.7836 |
95
+ | 0.3293 | 15.2889 | 860 | 2.7802 | 13.9120 |
96
+ | 0.3244 | 15.6444 | 880 | 2.7760 | 13.5101 |
97
+ | 0.3289 | 16.0 | 900 | 2.7884 | 13.5409 |
98
+ | 0.2768 | 16.3556 | 920 | 2.7946 | 13.7801 |
99
+ | 0.2825 | 16.7111 | 940 | 2.7988 | 14.1662 |
100
+ | 0.3059 | 17.0667 | 960 | 2.8092 | 13.6667 |
101
+ | 0.2279 | 17.4222 | 980 | 2.8253 | 13.7704 |
102
+ | 0.2283 | 17.7778 | 1000 | 2.8236 | 13.7256 |
103
+ | 0.2293 | 18.1333 | 1020 | 2.8174 | 13.1741 |
104
+ | 0.1934 | 18.4889 | 1040 | 2.8220 | 13.5479 |
105
+ | 0.1927 | 18.8444 | 1060 | 2.8225 | 13.6324 |
106
+ | 0.1794 | 19.2 | 1080 | 2.8343 | 13.4195 |
107
+ | 0.169 | 19.5556 | 1100 | 2.8345 | 13.3967 |
108
+ | 0.1724 | 19.9111 | 1120 | 2.8334 | 13.4415 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - Transformers 4.41.2
114
+ - Pytorch 2.3.0+cu121
115
+ - Datasets 2.20.0
116
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "position_embedding_type": "absolute",
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "float32",
25
- "transformers_version": "4.42.4",
26
  "use_cache": true,
27
  "vision_config": {
28
  "dropout": 0.0,
 
22
  "position_embedding_type": "absolute",
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "float32",
25
+ "transformers_version": "4.41.2",
26
  "use_cache": true,
27
  "vision_config": {
28
  "dropout": 0.0,
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 101,
4
+ "eos_token_id": 102,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.2"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d430d336d3812b2315bf2d4d09c7885621c868e9caa697ca1b8ece5c1052cbf
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d989efd9b066ace2c15f62a050a2049fba3c7984ca59559739a9c69a9c775b
3
  size 706516040
runs/Jul14_03-54-49_d666e0c03635/events.out.tfevents.1720929290.d666e0c03635.919.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86802d6a7b1502f9af787ba1b75940779c3cf580e00859fb9a100e7e01b2ea8f
3
- size 40449
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6551ae059a94767abe7e3d6e8b87c65c18e57b4113123fc454eddd1a93fec45
3
+ size 41338
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1744811e6c2a89fa3e5af3d4b8552560607c2d9da855629df82eb11dc066802
3
- size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd984a5a21fef4e1df1f4a378af4a4a61caa38a5ea60eefb784efeedb6522fc
3
+ size 5112